The U.S. Department of Energy today debuted a new portal called ScienceCinema that uses speech analysis and indexing technology from Microsoft Research to let people search the contents of scientific videos and presentations produced by the DOE National Laboratories and other DOE research sites.

ScienceCinema lets you to search videos for words and phrases spoken within the video files.

TechFlash says it the same technology that Washington state started piloting a couple years ago to let citizens search audio recordings from legislative sessions by keyword.

The Microsoft Research Audio Video Indexing System (MAVIS) is a set of software components that use speech recognition technology to enable searching of digitized spoken content, whether they are from meetings, conference calls, voice mails, presentations, online lectures, or even Internet video.

YouTube added a feature that generates video captions. They combined Google’s automatic speech recognition (ASR) technology with the YouTube caption system. YouTube began rolling out the robo-transcription option across its entire Web site, much to the delight of the speech technology community. Users can also add a transcript to each video file manually.

Adobe says you can transcribe spoken words to text and use Speech Search to find precise locations in clips using Premiere Pro. Speech Search makes editing clips of speaking talent quicker.

View full post on dailywireless.org